linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: Alexey Dobriyan <adobriyan@gmail.com>
Cc: tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
	hpa@zytor.com, x86@kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH] x86: drop REG_OUT macro from hweight functions
Date: Mon, 29 Jul 2019 12:04:47 +0200	[thread overview]
Message-ID: <20190729100447.GD31425@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20190729094329.GW31381@hirez.programming.kicks-ass.net>

On Mon, Jul 29, 2019 at 11:43:29AM +0200, Peter Zijlstra wrote:

> I _think_ something like the below should also work:
> 
> (fwiw _ASM_ARG 5 and 6 are broken, as are all the QLWB variants)

Fixed that, because

> ---
> diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
> index ba88edd0d58b..88704612b2f7 100644
> --- a/arch/x86/include/asm/arch_hweight.h
> +++ b/arch/x86/include/asm/arch_hweight.h
> @@ -3,22 +3,15 @@
>  #define _ASM_X86_HWEIGHT_H
>  
>  #include <asm/cpufeatures.h>
> -
> -#ifdef CONFIG_64BIT
> -#define REG_IN "D"
> -#define REG_OUT "a"
> -#else
> -#define REG_IN "a"
> -#define REG_OUT "a"
> -#endif
> +#include <asm/asm.h>
>  
>  static __always_inline unsigned int __arch_hweight32(unsigned int w)
>  {
>  	unsigned int res;
>  
>  	asm (ALTERNATIVE("call __sw_hweight32", "popcntl %1, %0", X86_FEATURE_POPCNT)
> -			 : "="REG_OUT (res)
> -			 : REG_IN (w));
> +			 : "=a" (res)
> +			 : _ASM_ARG1 (w));

That needs _ASM_ARG1L because popcntl..

---
diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index ba88edd0d58b..3cab7f382a43 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -3,22 +3,15 @@
 #define _ASM_X86_HWEIGHT_H
 
 #include <asm/cpufeatures.h>
-
-#ifdef CONFIG_64BIT
-#define REG_IN "D"
-#define REG_OUT "a"
-#else
-#define REG_IN "a"
-#define REG_OUT "a"
-#endif
+#include <asm/asm.h>
 
 static __always_inline unsigned int __arch_hweight32(unsigned int w)
 {
 	unsigned int res;
 
 	asm (ALTERNATIVE("call __sw_hweight32", "popcntl %1, %0", X86_FEATURE_POPCNT)
-			 : "="REG_OUT (res)
-			 : REG_IN (w));
+			 : "=a" (res)
+			 : _ASM_ARG1L (w));
 
 	return res;
 }
@@ -45,8 +38,8 @@ static __always_inline unsigned long __arch_hweight64(__u64 w)
 	unsigned long res;
 
 	asm (ALTERNATIVE("call __sw_hweight64", "popcntq %1, %0", X86_FEATURE_POPCNT)
-			 : "="REG_OUT (res)
-			 : REG_IN (w));
+			 : "=a" (res)
+			 : _ASM_ARG1 (w));
 
 	return res;
 }
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 3ff577c0b102..0bb0bbcd4551 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -53,17 +53,17 @@
 #define _ASM_ARG2	_ASM_DX
 #define _ASM_ARG3	_ASM_CX
 
-#define _ASM_ARG1L	eax
-#define _ASM_ARG2L	edx
-#define _ASM_ARG3L	ecx
+#define _ASM_ARG1L	_ASM_ARG1
+#define _ASM_ARG2L	_ASM_ARG2
+#define _ASM_ARG3L	_ASM_ARG3
 
-#define _ASM_ARG1W	ax
-#define _ASM_ARG2W	dx
-#define _ASM_ARG3W	cx
+#define _ASM_ARG1W	__ASM_FORM_RAW(ax)
+#define _ASM_ARG2W	__ASM_FORM_RAW(dx)
+#define _ASM_ARG3W	__ASM_FORM_RAW(cx)
 
-#define _ASM_ARG1B	al
-#define _ASM_ARG2B	dl
-#define _ASM_ARG3B	cl
+#define _ASM_ARG1B	__ASM_FORM_RAW(al)
+#define _ASM_ARG2B	__ASM_FORM_RAW(dl)
+#define _ASM_ARG3B	__ASM_FORM_RAW(cl)
 
 #else
 /* 64 bit */
@@ -72,36 +72,29 @@
 #define _ASM_ARG2	_ASM_SI
 #define _ASM_ARG3	_ASM_DX
 #define _ASM_ARG4	_ASM_CX
-#define _ASM_ARG5	r8
-#define _ASM_ARG6	r9
-
-#define _ASM_ARG1Q	rdi
-#define _ASM_ARG2Q	rsi
-#define _ASM_ARG3Q	rdx
-#define _ASM_ARG4Q	rcx
-#define _ASM_ARG5Q	r8
-#define _ASM_ARG6Q	r9
-
-#define _ASM_ARG1L	edi
-#define _ASM_ARG2L	esi
-#define _ASM_ARG3L	edx
-#define _ASM_ARG4L	ecx
-#define _ASM_ARG5L	r8d
-#define _ASM_ARG6L	r9d
-
-#define _ASM_ARG1W	di
-#define _ASM_ARG2W	si
-#define _ASM_ARG3W	dx
-#define _ASM_ARG4W	cx
-#define _ASM_ARG5W	r8w
-#define _ASM_ARG6W	r9w
-
-#define _ASM_ARG1B	dil
-#define _ASM_ARG2B	sil
-#define _ASM_ARG3B	dl
-#define _ASM_ARG4B	cl
-#define _ASM_ARG5B	r8b
-#define _ASM_ARG6B	r9b
+#define _ASM_ARG5	__ASM_REG(8)
+#define _ASM_ARG6	__ASM_REG(9)
+
+#define _ASM_ARG1L	__ASM_FORM_RAW(edi)
+#define _ASM_ARG2L	__ASM_FORM_RAW(esi)
+#define _ASM_ARG3L	__ASM_FORM_RAW(edx)
+#define _ASM_ARG4L	__ASM_FORM_RAW(ecx)
+#define _ASM_ARG5L	__ASM_FORM_RAW(r8d)
+#define _ASM_ARG6L	__ASM_FORM_RAW(r9d)
+
+#define _ASM_ARG1W	__ASM_FORM_RAW(di)
+#define _ASM_ARG2W	__ASM_FORM_RAW(si)
+#define _ASM_ARG3W	__ASM_FORM_RAW(dx)
+#define _ASM_ARG4W	__ASM_FORM_RAW(cx)
+#define _ASM_ARG5W	__ASM_FORM_RAW(r8w)
+#define _ASM_ARG6W	__ASM_FORM_RAW(r9w)
+
+#define _ASM_ARG1B	__ASM_FORM_RAW(dil)
+#define _ASM_ARG2B	__ASM_FORM_RAW(sil)
+#define _ASM_ARG3B	__ASM_FORM_RAW(dl)
+#define _ASM_ARG4B	__ASM_FORM_RAW(cl)
+#define _ASM_ARG5B	__ASM_FORM_RAW(r8b)
+#define _ASM_ARG6B	__ASM_FORM_RAW(r9b)
 
 #endif
 

  reply	other threads:[~2019-07-29 10:04 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-07-28 11:51 [PATCH] x86: drop REG_OUT macro from hweight functions Alexey Dobriyan
2019-07-29  9:43 ` Peter Zijlstra
2019-07-29 10:04   ` Peter Zijlstra [this message]
2019-07-29 20:44     ` Alexey Dobriyan
2019-07-30  8:08       ` Peter Zijlstra
2019-07-30 13:42         ` hpa

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190729100447.GD31425@hirez.programming.kicks-ass.net \
    --to=peterz@infradead.org \
    --cc=adobriyan@gmail.com \
    --cc=bp@alien8.de \
    --cc=hpa@zytor.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body. 
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).